AimeLaw / trainer_state.json
ductuan024's picture
Upload trainer_state.json
5cb5bc3
raw
history blame
26 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.687523259161477,
"global_step": 810000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04,
"learning_rate": 4.9824459158667857e-05,
"loss": 1.0594,
"step": 5000
},
{
"epoch": 0.07,
"learning_rate": 4.964891831733571e-05,
"loss": 1.0381,
"step": 10000
},
{
"epoch": 0.11,
"learning_rate": 4.947337747600357e-05,
"loss": 1.014,
"step": 15000
},
{
"epoch": 0.14,
"learning_rate": 4.9297836634671426e-05,
"loss": 0.9997,
"step": 20000
},
{
"epoch": 0.18,
"learning_rate": 4.912229579333928e-05,
"loss": 0.9936,
"step": 25000
},
{
"epoch": 0.21,
"learning_rate": 4.8946754952007134e-05,
"loss": 0.9765,
"step": 30000
},
{
"epoch": 0.25,
"learning_rate": 4.877121411067499e-05,
"loss": 0.975,
"step": 35000
},
{
"epoch": 0.28,
"learning_rate": 4.859567326934284e-05,
"loss": 0.9627,
"step": 40000
},
{
"epoch": 0.32,
"learning_rate": 4.84201324280107e-05,
"loss": 0.9641,
"step": 45000
},
{
"epoch": 0.35,
"learning_rate": 4.8244591586678564e-05,
"loss": 0.9562,
"step": 50000
},
{
"epoch": 0.39,
"learning_rate": 4.806905074534642e-05,
"loss": 0.9634,
"step": 55000
},
{
"epoch": 0.42,
"learning_rate": 4.789350990401427e-05,
"loss": 0.9532,
"step": 60000
},
{
"epoch": 0.46,
"learning_rate": 4.771796906268213e-05,
"loss": 0.9539,
"step": 65000
},
{
"epoch": 0.49,
"learning_rate": 4.754242822134998e-05,
"loss": 0.9599,
"step": 70000
},
{
"epoch": 0.53,
"learning_rate": 4.7366887380017835e-05,
"loss": 0.9437,
"step": 75000
},
{
"epoch": 0.56,
"learning_rate": 4.7191346538685696e-05,
"loss": 0.9395,
"step": 80000
},
{
"epoch": 0.6,
"learning_rate": 4.701580569735355e-05,
"loss": 0.9385,
"step": 85000
},
{
"epoch": 0.63,
"learning_rate": 4.6840264856021404e-05,
"loss": 0.947,
"step": 90000
},
{
"epoch": 0.67,
"learning_rate": 4.666472401468926e-05,
"loss": 0.9402,
"step": 95000
},
{
"epoch": 0.7,
"learning_rate": 4.648918317335711e-05,
"loss": 0.9317,
"step": 100000
},
{
"epoch": 0.74,
"learning_rate": 4.631364233202497e-05,
"loss": 0.9316,
"step": 105000
},
{
"epoch": 0.77,
"learning_rate": 4.613810149069283e-05,
"loss": 0.9399,
"step": 110000
},
{
"epoch": 0.81,
"learning_rate": 4.596256064936068e-05,
"loss": 0.9395,
"step": 115000
},
{
"epoch": 0.84,
"learning_rate": 4.5787019808028536e-05,
"loss": 0.9303,
"step": 120000
},
{
"epoch": 0.88,
"learning_rate": 4.561147896669639e-05,
"loss": 0.9304,
"step": 125000
},
{
"epoch": 0.91,
"learning_rate": 4.5435938125364244e-05,
"loss": 0.9126,
"step": 130000
},
{
"epoch": 0.95,
"learning_rate": 4.5260397284032105e-05,
"loss": 0.9165,
"step": 135000
},
{
"epoch": 0.98,
"learning_rate": 4.5084856442699966e-05,
"loss": 0.9311,
"step": 140000
},
{
"epoch": 1.02,
"learning_rate": 4.490931560136782e-05,
"loss": 0.9139,
"step": 145000
},
{
"epoch": 1.05,
"learning_rate": 4.4733774760035675e-05,
"loss": 0.9097,
"step": 150000
},
{
"epoch": 1.09,
"learning_rate": 4.455823391870353e-05,
"loss": 0.9086,
"step": 155000
},
{
"epoch": 1.12,
"learning_rate": 4.438269307737138e-05,
"loss": 0.9172,
"step": 160000
},
{
"epoch": 1.16,
"learning_rate": 4.420715223603924e-05,
"loss": 0.9106,
"step": 165000
},
{
"epoch": 1.19,
"learning_rate": 4.40316113947071e-05,
"loss": 0.9001,
"step": 170000
},
{
"epoch": 1.23,
"learning_rate": 4.385607055337495e-05,
"loss": 0.9108,
"step": 175000
},
{
"epoch": 1.26,
"learning_rate": 4.3680529712042806e-05,
"loss": 0.911,
"step": 180000
},
{
"epoch": 1.3,
"learning_rate": 4.350498887071066e-05,
"loss": 0.9007,
"step": 185000
},
{
"epoch": 1.33,
"learning_rate": 4.3329448029378515e-05,
"loss": 0.8908,
"step": 190000
},
{
"epoch": 1.37,
"learning_rate": 4.315390718804637e-05,
"loss": 0.897,
"step": 195000
},
{
"epoch": 1.4,
"learning_rate": 4.297836634671423e-05,
"loss": 0.902,
"step": 200000
},
{
"epoch": 1.44,
"learning_rate": 4.2802825505382084e-05,
"loss": 0.8918,
"step": 205000
},
{
"epoch": 1.47,
"learning_rate": 4.262728466404994e-05,
"loss": 0.889,
"step": 210000
},
{
"epoch": 1.51,
"learning_rate": 4.245174382271779e-05,
"loss": 0.8929,
"step": 215000
},
{
"epoch": 1.54,
"learning_rate": 4.2276202981385646e-05,
"loss": 0.8974,
"step": 220000
},
{
"epoch": 1.58,
"learning_rate": 4.210066214005351e-05,
"loss": 0.8932,
"step": 225000
},
{
"epoch": 1.61,
"learning_rate": 4.192512129872136e-05,
"loss": 0.8901,
"step": 230000
},
{
"epoch": 1.65,
"learning_rate": 4.174958045738922e-05,
"loss": 0.8849,
"step": 235000
},
{
"epoch": 1.69,
"learning_rate": 4.1574039616057077e-05,
"loss": 0.8801,
"step": 240000
},
{
"epoch": 1.72,
"learning_rate": 4.139849877472493e-05,
"loss": 0.8807,
"step": 245000
},
{
"epoch": 1.76,
"learning_rate": 4.1222957933392785e-05,
"loss": 0.8847,
"step": 250000
},
{
"epoch": 1.79,
"learning_rate": 4.104741709206064e-05,
"loss": 0.8753,
"step": 255000
},
{
"epoch": 1.83,
"learning_rate": 4.08718762507285e-05,
"loss": 0.8764,
"step": 260000
},
{
"epoch": 1.86,
"learning_rate": 4.0696335409396354e-05,
"loss": 0.8748,
"step": 265000
},
{
"epoch": 1.9,
"learning_rate": 4.052079456806421e-05,
"loss": 0.8789,
"step": 270000
},
{
"epoch": 1.93,
"learning_rate": 4.034525372673206e-05,
"loss": 0.875,
"step": 275000
},
{
"epoch": 1.97,
"learning_rate": 4.016971288539992e-05,
"loss": 0.8711,
"step": 280000
},
{
"epoch": 2.0,
"learning_rate": 3.999417204406777e-05,
"loss": 0.8688,
"step": 285000
},
{
"epoch": 2.04,
"learning_rate": 3.981863120273563e-05,
"loss": 0.8594,
"step": 290000
},
{
"epoch": 2.07,
"learning_rate": 3.9643090361403486e-05,
"loss": 0.8595,
"step": 295000
},
{
"epoch": 2.11,
"learning_rate": 3.946754952007134e-05,
"loss": 0.8536,
"step": 300000
},
{
"epoch": 2.14,
"learning_rate": 3.9292008678739194e-05,
"loss": 0.8618,
"step": 305000
},
{
"epoch": 2.18,
"learning_rate": 3.911646783740705e-05,
"loss": 0.8511,
"step": 310000
},
{
"epoch": 2.21,
"learning_rate": 3.894092699607491e-05,
"loss": 0.8543,
"step": 315000
},
{
"epoch": 2.25,
"learning_rate": 3.8765386154742763e-05,
"loss": 0.856,
"step": 320000
},
{
"epoch": 2.28,
"learning_rate": 3.8589845313410624e-05,
"loss": 0.8608,
"step": 325000
},
{
"epoch": 2.32,
"learning_rate": 3.841430447207848e-05,
"loss": 0.8449,
"step": 330000
},
{
"epoch": 2.35,
"learning_rate": 3.823876363074633e-05,
"loss": 0.8527,
"step": 335000
},
{
"epoch": 2.39,
"learning_rate": 3.806322278941419e-05,
"loss": 0.8441,
"step": 340000
},
{
"epoch": 2.42,
"learning_rate": 3.788768194808204e-05,
"loss": 0.8436,
"step": 345000
},
{
"epoch": 2.46,
"learning_rate": 3.77121411067499e-05,
"loss": 0.8448,
"step": 350000
},
{
"epoch": 2.49,
"learning_rate": 3.7536600265417756e-05,
"loss": 0.8348,
"step": 355000
},
{
"epoch": 2.53,
"learning_rate": 3.736105942408561e-05,
"loss": 0.8466,
"step": 360000
},
{
"epoch": 2.56,
"learning_rate": 3.7185518582753464e-05,
"loss": 0.8354,
"step": 365000
},
{
"epoch": 2.6,
"learning_rate": 3.700997774142132e-05,
"loss": 0.8421,
"step": 370000
},
{
"epoch": 2.63,
"learning_rate": 3.683443690008917e-05,
"loss": 0.8354,
"step": 375000
},
{
"epoch": 2.67,
"learning_rate": 3.6658896058757034e-05,
"loss": 0.8358,
"step": 380000
},
{
"epoch": 2.7,
"learning_rate": 3.648335521742489e-05,
"loss": 0.8414,
"step": 385000
},
{
"epoch": 2.74,
"learning_rate": 3.630781437609274e-05,
"loss": 0.8428,
"step": 390000
},
{
"epoch": 2.77,
"learning_rate": 3.6132273534760596e-05,
"loss": 0.8303,
"step": 395000
},
{
"epoch": 2.81,
"learning_rate": 3.595673269342845e-05,
"loss": 0.834,
"step": 400000
},
{
"epoch": 2.84,
"learning_rate": 3.578119185209631e-05,
"loss": 0.8311,
"step": 405000
},
{
"epoch": 2.88,
"learning_rate": 3.5605651010764165e-05,
"loss": 0.8245,
"step": 410000
},
{
"epoch": 2.91,
"learning_rate": 3.5430110169432026e-05,
"loss": 0.8211,
"step": 415000
},
{
"epoch": 2.95,
"learning_rate": 3.525456932809988e-05,
"loss": 0.8154,
"step": 420000
},
{
"epoch": 2.98,
"learning_rate": 3.5079028486767735e-05,
"loss": 0.8196,
"step": 425000
},
{
"epoch": 3.02,
"learning_rate": 3.490348764543559e-05,
"loss": 0.8188,
"step": 430000
},
{
"epoch": 3.05,
"learning_rate": 3.472794680410344e-05,
"loss": 0.81,
"step": 435000
},
{
"epoch": 3.09,
"learning_rate": 3.45524059627713e-05,
"loss": 0.8054,
"step": 440000
},
{
"epoch": 3.12,
"learning_rate": 3.437686512143916e-05,
"loss": 0.8156,
"step": 445000
},
{
"epoch": 3.16,
"learning_rate": 3.420132428010701e-05,
"loss": 0.8032,
"step": 450000
},
{
"epoch": 3.19,
"learning_rate": 3.4025783438774866e-05,
"loss": 0.8109,
"step": 455000
},
{
"epoch": 3.23,
"learning_rate": 3.385024259744272e-05,
"loss": 0.812,
"step": 460000
},
{
"epoch": 3.27,
"learning_rate": 3.3674701756110575e-05,
"loss": 0.8102,
"step": 465000
},
{
"epoch": 3.3,
"learning_rate": 3.3499160914778436e-05,
"loss": 0.8032,
"step": 470000
},
{
"epoch": 3.34,
"learning_rate": 3.332362007344629e-05,
"loss": 0.8098,
"step": 475000
},
{
"epoch": 3.37,
"learning_rate": 3.3148079232114144e-05,
"loss": 0.8057,
"step": 480000
},
{
"epoch": 3.41,
"learning_rate": 3.2972538390782e-05,
"loss": 0.8026,
"step": 485000
},
{
"epoch": 3.44,
"learning_rate": 3.279699754944985e-05,
"loss": 0.8039,
"step": 490000
},
{
"epoch": 3.48,
"learning_rate": 3.262145670811771e-05,
"loss": 0.8024,
"step": 495000
},
{
"epoch": 3.51,
"learning_rate": 3.244591586678557e-05,
"loss": 0.8018,
"step": 500000
},
{
"epoch": 3.55,
"learning_rate": 3.227037502545343e-05,
"loss": 0.7953,
"step": 505000
},
{
"epoch": 3.58,
"learning_rate": 3.209483418412128e-05,
"loss": 0.7895,
"step": 510000
},
{
"epoch": 3.62,
"learning_rate": 3.191929334278914e-05,
"loss": 0.7878,
"step": 515000
},
{
"epoch": 3.65,
"learning_rate": 3.174375250145699e-05,
"loss": 0.794,
"step": 520000
},
{
"epoch": 3.69,
"learning_rate": 3.1568211660124845e-05,
"loss": 0.7998,
"step": 525000
},
{
"epoch": 3.72,
"learning_rate": 3.13926708187927e-05,
"loss": 0.7819,
"step": 530000
},
{
"epoch": 3.76,
"learning_rate": 3.121712997746056e-05,
"loss": 0.7917,
"step": 535000
},
{
"epoch": 3.79,
"learning_rate": 3.1041589136128414e-05,
"loss": 0.7827,
"step": 540000
},
{
"epoch": 3.83,
"learning_rate": 3.086604829479627e-05,
"loss": 0.7874,
"step": 545000
},
{
"epoch": 3.86,
"learning_rate": 3.069050745346412e-05,
"loss": 0.7788,
"step": 550000
},
{
"epoch": 3.9,
"learning_rate": 3.051496661213198e-05,
"loss": 0.7821,
"step": 555000
},
{
"epoch": 3.93,
"learning_rate": 3.0339425770799834e-05,
"loss": 0.7828,
"step": 560000
},
{
"epoch": 3.97,
"learning_rate": 3.016388492946769e-05,
"loss": 0.7769,
"step": 565000
},
{
"epoch": 4.0,
"learning_rate": 2.9988344088135546e-05,
"loss": 0.7779,
"step": 570000
},
{
"epoch": 4.04,
"learning_rate": 2.98128032468034e-05,
"loss": 0.7633,
"step": 575000
},
{
"epoch": 4.07,
"learning_rate": 2.963726240547126e-05,
"loss": 0.765,
"step": 580000
},
{
"epoch": 4.11,
"learning_rate": 2.9461721564139115e-05,
"loss": 0.7614,
"step": 585000
},
{
"epoch": 4.14,
"learning_rate": 2.9286180722806973e-05,
"loss": 0.7669,
"step": 590000
},
{
"epoch": 4.18,
"learning_rate": 2.9110639881474827e-05,
"loss": 0.7721,
"step": 595000
},
{
"epoch": 4.21,
"learning_rate": 2.893509904014268e-05,
"loss": 0.7633,
"step": 600000
},
{
"epoch": 4.25,
"learning_rate": 2.875955819881054e-05,
"loss": 0.7618,
"step": 605000
},
{
"epoch": 4.28,
"learning_rate": 2.8584017357478393e-05,
"loss": 0.7603,
"step": 610000
},
{
"epoch": 4.32,
"learning_rate": 2.8408476516146247e-05,
"loss": 0.7594,
"step": 615000
},
{
"epoch": 4.35,
"learning_rate": 2.8232935674814104e-05,
"loss": 0.7612,
"step": 620000
},
{
"epoch": 4.39,
"learning_rate": 2.805739483348196e-05,
"loss": 0.7616,
"step": 625000
},
{
"epoch": 4.42,
"learning_rate": 2.7881853992149816e-05,
"loss": 0.7628,
"step": 630000
},
{
"epoch": 4.46,
"learning_rate": 2.770631315081767e-05,
"loss": 0.7638,
"step": 635000
},
{
"epoch": 4.49,
"learning_rate": 2.7530772309485525e-05,
"loss": 0.7469,
"step": 640000
},
{
"epoch": 4.53,
"learning_rate": 2.7355231468153382e-05,
"loss": 0.7477,
"step": 645000
},
{
"epoch": 4.56,
"learning_rate": 2.7179690626821236e-05,
"loss": 0.7501,
"step": 650000
},
{
"epoch": 4.6,
"learning_rate": 2.700414978548909e-05,
"loss": 0.7513,
"step": 655000
},
{
"epoch": 4.63,
"learning_rate": 2.6828608944156948e-05,
"loss": 0.751,
"step": 660000
},
{
"epoch": 4.67,
"learning_rate": 2.6653068102824802e-05,
"loss": 0.7491,
"step": 665000
},
{
"epoch": 4.7,
"learning_rate": 2.6477527261492663e-05,
"loss": 0.7516,
"step": 670000
},
{
"epoch": 4.74,
"learning_rate": 2.6301986420160517e-05,
"loss": 0.7511,
"step": 675000
},
{
"epoch": 4.74,
"eval_loss": 0.6953830122947693,
"eval_runtime": 12.1778,
"eval_samples_per_second": 82.116,
"eval_steps_per_second": 10.265,
"step": 675000
},
{
"epoch": 4.77,
"learning_rate": 2.6126445578828375e-05,
"loss": 0.7395,
"step": 680000
},
{
"epoch": 4.77,
"eval_loss": 0.6852219104766846,
"eval_runtime": 12.2181,
"eval_samples_per_second": 81.846,
"eval_steps_per_second": 10.231,
"step": 680000
},
{
"epoch": 4.81,
"learning_rate": 2.595090473749623e-05,
"loss": 0.7445,
"step": 685000
},
{
"epoch": 4.81,
"eval_loss": 0.7140026688575745,
"eval_runtime": 12.2246,
"eval_samples_per_second": 81.802,
"eval_steps_per_second": 10.225,
"step": 685000
},
{
"epoch": 4.84,
"learning_rate": 2.5775363896164083e-05,
"loss": 0.7448,
"step": 690000
},
{
"epoch": 4.84,
"eval_loss": 0.678001880645752,
"eval_runtime": 12.1996,
"eval_samples_per_second": 81.97,
"eval_steps_per_second": 10.246,
"step": 690000
},
{
"epoch": 4.88,
"learning_rate": 2.559982305483194e-05,
"loss": 0.7392,
"step": 695000
},
{
"epoch": 4.88,
"eval_loss": 0.6525120139122009,
"eval_runtime": 12.2116,
"eval_samples_per_second": 81.889,
"eval_steps_per_second": 10.236,
"step": 695000
},
{
"epoch": 4.92,
"learning_rate": 2.5424282213499795e-05,
"loss": 0.7499,
"step": 700000
},
{
"epoch": 4.92,
"eval_loss": 0.6543171405792236,
"eval_runtime": 12.2207,
"eval_samples_per_second": 81.828,
"eval_steps_per_second": 10.229,
"step": 700000
},
{
"epoch": 4.95,
"learning_rate": 2.524874137216765e-05,
"loss": 0.7393,
"step": 705000
},
{
"epoch": 4.95,
"eval_loss": 0.665242075920105,
"eval_runtime": 5.3758,
"eval_samples_per_second": 186.02,
"eval_steps_per_second": 23.253,
"step": 705000
},
{
"epoch": 4.99,
"learning_rate": 2.5073200530835506e-05,
"loss": 0.7324,
"step": 710000
},
{
"epoch": 4.99,
"eval_loss": 0.6618428826332092,
"eval_runtime": 5.3906,
"eval_samples_per_second": 185.507,
"eval_steps_per_second": 23.188,
"step": 710000
},
{
"epoch": 5.02,
"learning_rate": 2.489765968950336e-05,
"loss": 0.7261,
"step": 715000
},
{
"epoch": 5.02,
"eval_loss": 0.6423526406288147,
"eval_runtime": 5.3892,
"eval_samples_per_second": 185.555,
"eval_steps_per_second": 23.194,
"step": 715000
},
{
"epoch": 5.06,
"learning_rate": 2.4722118848171215e-05,
"loss": 0.7327,
"step": 720000
},
{
"epoch": 5.06,
"eval_loss": 0.6585870385169983,
"eval_runtime": 5.3853,
"eval_samples_per_second": 185.69,
"eval_steps_per_second": 23.211,
"step": 720000
},
{
"epoch": 5.09,
"learning_rate": 2.4546578006839072e-05,
"loss": 0.7265,
"step": 725000
},
{
"epoch": 5.09,
"eval_loss": 0.6187921762466431,
"eval_runtime": 5.3825,
"eval_samples_per_second": 185.787,
"eval_steps_per_second": 23.223,
"step": 725000
},
{
"epoch": 5.13,
"learning_rate": 2.4371037165506926e-05,
"loss": 0.7247,
"step": 730000
},
{
"epoch": 5.13,
"eval_loss": 0.6582339406013489,
"eval_runtime": 5.3823,
"eval_samples_per_second": 185.796,
"eval_steps_per_second": 23.224,
"step": 730000
},
{
"epoch": 5.16,
"learning_rate": 2.419549632417478e-05,
"loss": 0.7265,
"step": 735000
},
{
"epoch": 5.16,
"eval_loss": 0.7226254940032959,
"eval_runtime": 5.3797,
"eval_samples_per_second": 185.883,
"eval_steps_per_second": 23.235,
"step": 735000
},
{
"epoch": 5.2,
"learning_rate": 2.401995548284264e-05,
"loss": 0.7166,
"step": 740000
},
{
"epoch": 5.2,
"eval_loss": 0.6698991656303406,
"eval_runtime": 5.3768,
"eval_samples_per_second": 185.986,
"eval_steps_per_second": 23.248,
"step": 740000
},
{
"epoch": 5.23,
"learning_rate": 2.3844414641510496e-05,
"loss": 0.7214,
"step": 745000
},
{
"epoch": 5.23,
"eval_loss": 0.6653444170951843,
"eval_runtime": 5.3777,
"eval_samples_per_second": 185.954,
"eval_steps_per_second": 23.244,
"step": 745000
},
{
"epoch": 5.27,
"learning_rate": 2.366887380017835e-05,
"loss": 0.7268,
"step": 750000
},
{
"epoch": 5.27,
"eval_loss": 0.6490678787231445,
"eval_runtime": 5.3962,
"eval_samples_per_second": 185.314,
"eval_steps_per_second": 23.164,
"step": 750000
},
{
"epoch": 5.3,
"learning_rate": 2.3493332958846207e-05,
"loss": 0.7177,
"step": 755000
},
{
"epoch": 5.3,
"eval_loss": 0.6720253825187683,
"eval_runtime": 5.3813,
"eval_samples_per_second": 185.828,
"eval_steps_per_second": 23.229,
"step": 755000
},
{
"epoch": 5.34,
"learning_rate": 2.331779211751406e-05,
"loss": 0.7173,
"step": 760000
},
{
"epoch": 5.34,
"eval_loss": 0.636309027671814,
"eval_runtime": 5.3741,
"eval_samples_per_second": 186.079,
"eval_steps_per_second": 23.26,
"step": 760000
},
{
"epoch": 5.37,
"learning_rate": 2.3142251276181916e-05,
"loss": 0.7222,
"step": 765000
},
{
"epoch": 5.37,
"eval_loss": 0.6736326813697815,
"eval_runtime": 5.3844,
"eval_samples_per_second": 185.723,
"eval_steps_per_second": 23.215,
"step": 765000
},
{
"epoch": 5.41,
"learning_rate": 2.2966710434849773e-05,
"loss": 0.7189,
"step": 770000
},
{
"epoch": 5.41,
"eval_loss": 0.6502253413200378,
"eval_runtime": 5.3808,
"eval_samples_per_second": 185.846,
"eval_steps_per_second": 23.231,
"step": 770000
},
{
"epoch": 5.44,
"learning_rate": 2.2791169593517627e-05,
"loss": 0.7142,
"step": 775000
},
{
"epoch": 5.44,
"eval_loss": 0.6675522327423096,
"eval_runtime": 5.3769,
"eval_samples_per_second": 185.982,
"eval_steps_per_second": 23.248,
"step": 775000
},
{
"epoch": 5.48,
"learning_rate": 2.2615628752185485e-05,
"loss": 0.7123,
"step": 780000
},
{
"epoch": 5.48,
"eval_loss": 0.7307547330856323,
"eval_runtime": 5.3752,
"eval_samples_per_second": 186.041,
"eval_steps_per_second": 23.255,
"step": 780000
},
{
"epoch": 5.51,
"learning_rate": 2.2440087910853343e-05,
"loss": 0.7149,
"step": 785000
},
{
"epoch": 5.51,
"eval_loss": 0.6528046727180481,
"eval_runtime": 5.3874,
"eval_samples_per_second": 185.618,
"eval_steps_per_second": 23.202,
"step": 785000
},
{
"epoch": 5.55,
"learning_rate": 2.2264547069521197e-05,
"loss": 0.7111,
"step": 790000
},
{
"epoch": 5.55,
"eval_loss": 0.6415424942970276,
"eval_runtime": 5.3848,
"eval_samples_per_second": 185.708,
"eval_steps_per_second": 23.213,
"step": 790000
},
{
"epoch": 5.58,
"learning_rate": 2.208900622818905e-05,
"loss": 0.7126,
"step": 795000
},
{
"epoch": 5.58,
"eval_loss": 0.664243221282959,
"eval_runtime": 5.3818,
"eval_samples_per_second": 185.812,
"eval_steps_per_second": 23.226,
"step": 795000
},
{
"epoch": 5.62,
"learning_rate": 2.191346538685691e-05,
"loss": 0.7075,
"step": 800000
},
{
"epoch": 5.62,
"eval_loss": 0.6190058588981628,
"eval_runtime": 5.3768,
"eval_samples_per_second": 185.985,
"eval_steps_per_second": 23.248,
"step": 800000
},
{
"epoch": 5.65,
"learning_rate": 2.1737924545524763e-05,
"loss": 0.7047,
"step": 805000
},
{
"epoch": 5.65,
"eval_loss": 0.645745038986206,
"eval_runtime": 5.3814,
"eval_samples_per_second": 185.824,
"eval_steps_per_second": 23.228,
"step": 805000
},
{
"epoch": 5.69,
"learning_rate": 2.1562383704192617e-05,
"loss": 0.7002,
"step": 810000
},
{
"epoch": 5.69,
"eval_loss": 0.6156101226806641,
"eval_runtime": 5.3698,
"eval_samples_per_second": 186.226,
"eval_steps_per_second": 23.278,
"step": 810000
}
],
"max_steps": 1424170,
"num_train_epochs": 10,
"total_flos": 3.3150958919481446e+17,
"trial_name": null,
"trial_params": null
}